基于序列轮廓线的凸面目标全自动重构方法

周朗明; 张小虎; 关棒磊

doi:10.16383/j.aas.2015.c140369

基于序列轮廓线的凸面目标全自动重构方法

doi: 10.16383/j.aas.2015.c140369

周朗明^1,2, ,,
张小虎^1,2,
关棒磊^1,2

1.
国防科学技术大学航天科学与工程学院长沙 410073;
2.
湖南省图像测量与视觉导航重点实验室长沙 410073

基金项目:

国家自然科学基金(11272347),国家重大科学仪器设备开发专项(2013YQ140517)资助

详细信息

作者简介:
张小虎国防科学技术大学航天科学与工程学院研究员.主要研究方向为摄像测量与计算机视觉.E-mail:zxh1302@hotmail.com

通讯作者:
周朗明国防科学技术大学航天科学与工程学院博士后.主要研究方向为数字摄影测量与计算机视觉.本文通信作者.E-mail:zlm_mj@126.com

计量
- 文章访问数: 1647
- HTML全文浏览量: 76
- PDF下载量: 1325
- 被引次数: 54
出版历程
- 收稿日期: 2014-06-03
- 修回日期: 2014-11-15
- 刊出日期: 2015-04-20

An Automatic Reconstruction Method of Convex Object Based on Sequence Contours

1.
College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073;
2.
Hunan Provincial Key Laboratory of Image Measurement and Vision Navigation, Changsha 410073

Funds:

Supported by National Natural Science Foundation of China(11272347), and National Key Scientific Instrument and Equipment Development Project(2013YQ140517)

摘要

摘要: 凸面目标在成像时会表现尺寸较小、纹理稀疏或缺乏、透光、反光等特点.在对其进行三维重构时,传统的立体视觉匹配、主动视觉扫描(激光或结构光)等重构方法无法提供良好的解决方案.针对此类目标的重构难题,本文提出一种基于序列轮廓线的全自动重构方法.该方法首先采集目标的序列轮廓影像,然后提取高精度的轮廓线,再利用多个视角的轮廓线对初始外包体进行空间切割得到目标的初始三维模型,接着根据角度和面积约束对初始三维模型中的面进行合并,最后利用合并后的面重新对外包体进行精细切割得到目标的精确三维刻面模型.通过对凸面目标(注射器针头,直径约为3mm)的重构实验证明,利用本文的方法重构得到的模型角度误差小于0.7,执行时间小于15s,重构过程无需人工干预,能有效解决凸面目标的三维重构及视觉测量难题.
- 计算机视觉 /
- 序列轮廓线 /
- 空间切割 /
- 凸面目标 /
- 轮廓重构 /
- 视觉测量
Abstract: There is a small size, lack of or less texture, transparent and reflective phenomenon on the images of convex objects. So the traditional reconstruction methods such as stereo-vision matching and active vision scanning such as laser or structure light cannot be used for such objects. In this paper, a reconstruction method based on multi-contours for miniature convex object is proposed. Firstly, multi-view silhouette images are captured, then the accurate contours are extracted; secondly coarse mesh is generated by space carving of multi-contours, and thirdly, the fragmented polygons are merged according to angle and area constriants; at last, the accurate mesh is generated by space carving of multi-polygons of the coarse mesh. The reconstruction experiments of regular and convex objects(syringe needle, diameter is about 3mm) proved that the angular error is less than 0.7 and the time cost is less than 15 seconds and the total process is without manual intervention. This method can solve the problem of reconstruction and vision measurement of convex objects effectively.
- Computer vision /
- sequence contours /
- space carving /
- convex object /
- SFS /
- vision measurement

HTML全文

参考文献(36)

[1]	Wang C, Yang W M, Liao Q M. A space carving based reconstruction method using discrete viewing. In:Proceedings of the 7th International Conference on Image and Graphics. Qingdao, China:IEEE, 2013. 607-611
[2]	Liu Guang-Shuai, Li Bai-Lin, He Chao-Ming. Convex optimization of continuous energy model in multiview 3D reconstruction. Computer Engineering and Applications, 2013, 49(1):19-22(刘光帅, 李柏林, 何朝明. 多视三维重构中连续能量模型的凸优化. 计算机工程与应用, 2013, 49(1):19-22)
[3]	[3] Yemez Y, Sahillioglu Y. Shape from silhouette using topology-adaptive mesh deformation. Pattern Recognition Letters, 2009, 30(13):1198-1207
[4]	[4] Dyer C R. Volumetric scene reconstruction from multiple views. Foundations of Image Understanding, 2001, 628:469-489
[5]	[5] Lorensen W E, Cline H E. Marching cubes:a high resolution 3d surface reconstruction algorithm. ACM Computer Graphics, 1987, 21(4):163-169
[6]	[6] Seitz S M, Dyer C R. Photorealistic scene reconstruction by voxel coloring. International Journal of Computer Vision, 1999, 35(2):151-173
[7]	[7] Kutulakos K N, Seitz S M. A theory of shape by space carving. International Journal of Computer Vision, 2000, 38(3):1999-2218
[8]	[8] Rankin J R, Boyapati M. Visual hull construction from semitransparent coloured silhouettes. International Journal of Computer Graphics Animation, 2013, 3(4):57-63
[9]	[9] Hernandez Esteban C, Schmitt F. Multi-stereo 3D object reconstruction. In:Proceedings of the 1st International Symposium on 3D Data Processing Visualization and Transmission. Padova, Italy:IEEE, 2002. 159-166
[10]	Mulayim A Y, Yilmaz U, Atalay V. Silhouette-based 3-D model reconstruction from multiple images. IEEE Transactions on Systems, Man, and Cybernetics, 2003, 33(4):582-591
[11]	Wu C L, Wilburn B, Matsushita Y, Theobalt C. High-quality shape from multi-view stereo and shading under general illumination. In:Proceedings of the 2011 Conference on Computer Vision and Pattern Recognition Workshops. Colorado, USA:IEEE, 2011. 969-976
[12]	Cremers D, Kolev K. Multiview stereo and silhouette consistency via convex functionals over convex domains. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(6):1161-1174
[13]	Ladikos A, Benhimane S, Navab N. Efficient visual hull computation for real-time 3D reconstruction using CUDA. In:Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. Anchorage, AK, USA:IEEE, 2008. 1-8
[14]	Chang B, Woo S, Ihm I. GPU-based parallel construction of compact visual hull meshes. The Visual Computer, 2014, 30(2):201-211
[15]	Huang C H, Lu D M, Diao C Y. Accelerated visual hulls of complex objects using contribution weights. In:Proceedings of the 7th International Conference on Image and Graphics. Qingdao, China:IEEE, 2013. 685-689
[16]	Hours J H, Schorsch S, Jones C N. Parametric polytope reconstruction an application to crystal shape estimation. IEEE Transactions on Image Process, 2013, 30(2):201-211
[17]	Franco J, Boyer E. Efficient polyhedral modeling from silhouettes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(3):414-427
[18]	Matsumoto Y, Terasaki H, Sugimoto K, Arakawa T. A portable three-dimensional digitizer. In:Proceedings of the 1997 International Conference on Recent Advances in 3-D Digital Imaging and Modeling. Ottawa, Ont., Canada:IEEE, 1997. 197-204
[19]	Niem W. Automatic reconstruction of 3D objects using a mobile camera. Image and Vision Computing, 1999, 17(2):125-134
[20]	Schmitt F, Yemez Y. 3D color object reconstruction from 2D image sequences. In:Proceedings of the 1999 International Conference on Image Processing. Kobe, Japan:IEEE, 1999. 65-69
[21]	Slabaugh G, Schafer R, Hans M. Image-based photo hulls. In:Proceedings of the 1st International Symposium on 3D Data Processing Visualization and Transmission. Padova, Italy:IEEE, 2002. 704-862
[22]	Montani C, Scateni R, Scopigno R. Discretized marching cubes. In:Proceedings of the 1994 IEEE Conference on Visualization'94. Washington, D.C., USA:IEEE, 1994. 281-287
[23]	Cheung K, Baker S, Kanade T. Shape-from-silhouette of articulated objects and its use for human body kinematics estimation and motion capture. Computer Vision and Pattern Recognition, 2003, 1:77-84
[24]	Zhang Jian-Qing, Su Guo-Zhong, Zheng Shun-Yi, Zhong Liang. High accurate outline detection algorithm based on line diffusion function model. Geomatics and Information Science of Wuhan University, 2006, 31(2):95-104(张剑清, 苏国中, 郑顺义, 钟良. 基于线扩散函数的高精度轮廓特征提取算法. 武汉大学学报(信息科学版), 2006, 31(2):95-104)
[25]	Li Cai-Lin, Guo Bao-Yun, Li Chang. The high-accurate extraction of line features of object contour. Acta Geodaetica et Cartographica Sinica, 2011, 40(1):66-70(李彩林, 郭宝云, 李畅. 目标轮廓直线特征的高精度提取. 测绘学报, 2011, 40(1):66-70)
[26]	Zheng S Y, Li C L, Su G Z, Zhang J Q. High-accurate line feature extraction algorithm based on line diffusion function model. In:Proceedings of the 2007 International Symposium on Multispectral Image Processing and Pattern Recognition. Wuhan, China:SPIE, 2007. 678-683
[27]	Xu Ying-Xin, Li Xing-Fei, Zhu Jia. Application of telecentric lens in rotary workpiece measurement system. Transducer and Microsystem Technologies, 2010, 29(1):111-113(徐颖欣, 李醒飞, 朱嘉. 远心镜头在回转体测量系统中的应用. 传感器与微系统, 2010, 29(1):111-113)
[28]	Fremont V, Chellali R. Turntable-based 3D object reconstruction. In:Proceedings of the 2004 IEEE Conference on Cybernetics and Intelligent Systems. Singapore:IEEE, 2004. 1277-1282
[29]	Beardsley P A, Torr P H S, Zisserman A. 3D model acquisition from extended image sequences. In:Proceedings of the 4th European Conference on Computer Vision-ECCV'96. Berlin Heidelberg:Springer-Verlag, 1996. 683-695
[30]	Fitzgibbon A W, Cross G, Zisserman A. Automatic 3D model construction for turn-table sequences. In:Proceedings of the 1998 the European Workshop on 3D Structure from Multiple Images of Large-Scale Environments. Berlin Heidelberg:Springer-Verlag, 1998. 155-170
[31]	Eisert P, Steinbach E, Girod B. Automatic reconstruction of stationary 3-D objects from multiple uncalibrated camera views. IEEE Transactions on Circuits and Systems for Video Technology, 2000, 10(2):261-277
[32]	Gardner R J, Paolo G, Thorsten T. Determining a rotation of a tetrahedron from a projection. Discrete Computational Geometry, 2012, 48(3):749-765
[33]	Presles B, Debayle J, Pinoli J C. Size and shape estimation of 3-D convex objects from their 2-D projections:application to crystallization processes. Journal of Microscopy, 2012, 248(2):140-155
[34]	Lin T H, Chang H T, Hu S J. 3D reconstruction of intricate objects using planar cast shadows. In:Proceedings of the 2013 ACM SIGGRAPH 2013 Posters. New York, NY, USA:ACM, 2013. 78-88
[35]	Servin M, Garnica G, Estrada J C, Padilla J M. High-resolution low-noise 360-degree digital solid reconstruction using phase-stepping profilometry. Optics Express, 2014, 22(9):10914-10922
[36]	Xiong Bang-Shu, Yu Liang, Ou Qiao-Feng, Du Jing. An image-based quality detection method of syringe needles. Chinese Journal of Biomedical Engineering, 2010, 29(4):627-631(熊邦书, 余亮, 欧巧凤, 杜静. 注射器针头合格性图像检测方法. 中国生物医学工程学报, 2010, 29(4):627-631)

施引文献

期刊类型引用(15)

1.	张哲绎，梁博超，齐泽萱，王彩苗，唐洪霞，任飞. 基于RGBD与MVS三维重建技术的3D打印机逆反馈系统. 现代制造工程. 2023(10): 35-43 . 百度学术
2.	薛凡喜，张磊，沙建军，徐翔云，姜超. 面向地面工程目标物理毁伤特征分析的图像处理算法研究与系统开发. 防护工程. 2022(02): 37-42 . 百度学术
3.	郁钱，路金晓，柏基权，范洪辉. 基于深度学习的三维物体重建方法研究综述. 江苏理工学院学报. 2022(04): 31-41 . 百度学术
4.	蒋罕寒，郭锐，武军安，赵旭. 高旋掠飞弹载激光雷达稀疏点云插值算法. 弹箭与制导学报. 2021(01): 120-123 . 百度学术
5.	胡新荣，曾潇，刘军平，彭涛，何儒汉，陈常念. 多视角单目服装图像三维重建算法的研究与实现. 现代纺织技术. 2021(06): 84-90 . 百度学术
6.	蔚增岩，姜涛，胡作勇，赵天成. 基于轨道环境特征的轨道环境识别. 长春理工大学学报(自然科学版). 2020(06): 66-71 . 百度学术
7.	陈加，张玉麒，宋鹏，魏艳涛，王煜. 深度学习在基于单幅图像的物体三维重建中的应用. 自动化学报. 2019(04): 657-668 . 本站查看
8.	段志鑫，白志辉，陈冉丽，吴侃，周大伟. 基于多视影像的相似材料模型三维重建方法. 激光杂志. 2018(08): 137-141 . 百度学术
9.	蒙山，唐文名. 单目SLAM直线匹配增强平面发现方法. 北京航空航天大学学报. 2017(04): 660-666 . 百度学术
10.	郭萌，胡辽林，李捷. 基于多幅图像的陶瓷碗表面缺陷的局部点云重建. 光学学报. 2017(12): 247-253 . 百度学术
11.	李康，周泩朴，邹林波，邓鹏，耿国华. 基于无人机的大场景序列图像自动采集和三维建模. 西北大学学报(自然科学版). 2017(01): 30-37 . 百度学术
12.	郭保青，余祖俊，张楠，朱力强，高晨光. 铁路场景三维点云分割与分类识别算法. 仪器仪表学报. 2017(09): 2103-2111 . 百度学术
13.	徐旭东，李泽. 三维激光点云数据的可视化研究. 计算机科学. 2016(S1): 175-178 . 百度学术
14.	程健，祖丰收，王东伟，毛少文，马永辉，钱建生. 露天储煤场无人机自动盘煤系统研究. 煤炭科学技术. 2016(05): 160-165 . 百度学术
15.	陈明伟，杨洋. 基于张量投票和深度图的弱纹理图像三维重构. 系统仿真学报. 2015(10): 2553-2559 . 百度学术